© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14468
    Prev
    Next
    INDEX
    Explanations

    otherwise

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting conditions and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phony
    0.42
     ყ
    0.41
     fake
    0.41
     नकली
    0.40
     cheesy
    0.40
    FAKE
    0.39
    %%%%%%%%
    0.38
     sham
    0.38
    =========
    0.38
     jet
    0.38
    POSITIVE LOGITS
    otherwise
    0.87
     otherwise
    0.86
    Otherwise
    0.80
     Otherwise
    0.79
    否则
    0.77
     अन्यथा
    0.75
     নইলে
    0.73
     OTHERWISE
    0.67
     sonst
    0.62
     वरना
    0.61
    Activations Density 0.224%

    No Known Activations